© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39714
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     part
    -0.30
    éĥ¨åĪĨ
    -0.25
    .JWT
    -0.25
    éĥ¨ä»½
    -0.24
    miss
    -0.24
    oron
    -0.23
    ä½İä¼°
    -0.23
    (stdin
    -0.23
    èĢħ
    -0.23
    nowrap
    -0.23
    POSITIVE LOGITS
    ToF
    0.29
    éĥ´å·ŀ
    0.28
    沧å·ŀ
    0.27
    èĩ¼
    0.27
    StateMachine
    0.26
    mani
    0.26
    建
    0.25
     Tags
    0.25
     whites
    0.25
     backend
    0.25
    Activations Density 0.954%

    No Known Activations

    This feature has no known activations.